Auto prompting without training labels: An LLM cascade for product quality assessment in e-commerce catalogs
This addresses the challenge of scaling domain-specific quality assessment in industrial e-commerce catalogs with reduced human effort, though it is incremental as it builds on existing prompting techniques.
The paper tackles the problem of assessing product quality in e-commerce catalogs without training labels by introducing a training-free auto-prompting cascade for LLMs, resulting in an 8-10% improvement in precision and recall over traditional methods and a 99% reduction in expert effort from 5.1 hours to 3 minutes per attribute.
We introduce a novel, training free cascade for auto-prompting Large Language Models (LLMs) to assess product quality in e-commerce. Our system requires no training labels or model fine-tuning, instead automatically generating and refining prompts for evaluating attribute quality across tens of thousands of product category-attribute pairs. Starting from a seed of human-crafted prompts, the cascade progressively optimizes instructions to meet catalog-specific requirements. This approach bridges the gap between general language understanding and domain-specific knowledge at scale in complex industrial catalogs. Our extensive empirical evaluations shows the auto-prompt cascade improves precision and recall by $8-10\%$ over traditional chain-of-thought prompting. Notably, it achieves these gains while reducing domain expert effort from 5.1 hours to 3 minutes per attribute - a $99\%$ reduction. Additionally, the cascade generalizes effectively across five languages and multiple quality assessment tasks, consistently maintaining performance gains.